Sky's picture

Sky

dandingsky

·

dandingsky

AI & ML interests

None yet

Recent Activity

commented on a paper 5 days ago

Progressive Residual Warmup for Language Model Pretraining

submitted a paper 6 days ago

Progressive Residual Warmup for Language Model Pretraining

authored a paper 9 days ago

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners

View all activity

Organizations

upvoted a paper 9 days ago

Progressive Residual Warmup for Language Model Pretraining

Paper • 2603.05369 • Published 10 days ago • 32

upvoted a paper 30 days ago

Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models

Paper • 2602.12036 • Published about 1 month ago • 91

upvoted a paper 5 months ago

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners

Paper • 2509.26226 • Published Sep 30, 2025 • 34

upvoted a paper 10 months ago

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Paper • 2505.24864 • Published May 30, 2025 • 144